CN117634322B - Infrared LED facula parameter optimization method and related device - Google Patents
Infrared LED facula parameter optimization method and related device Download PDFInfo
- Publication number
- CN117634322B CN117634322B CN202410104621.8A CN202410104621A CN117634322B CN 117634322 B CN117634322 B CN 117634322B CN 202410104621 A CN202410104621 A CN 202410104621A CN 117634322 B CN117634322 B CN 117634322B
- Authority
- CN
- China
- Prior art keywords
- light spot
- infrared led
- data
- parameter
- spot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000011156 evaluation Methods 0.000 claims abstract description 85
- 238000012545 processing Methods 0.000 claims abstract description 34
- 238000013433 optimization analysis Methods 0.000 claims abstract description 12
- 230000007246 mechanism Effects 0.000 claims description 52
- 239000013598 vector Substances 0.000 claims description 48
- 238000004422 calculation algorithm Methods 0.000 claims description 43
- 238000004088 simulation Methods 0.000 claims description 37
- 238000012360 testing method Methods 0.000 claims description 31
- 238000009826 distribution Methods 0.000 claims description 29
- 238000013210 evaluation model Methods 0.000 claims description 25
- 238000013135 deep learning Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 18
- 230000003287 optical effect Effects 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000008447 perception Effects 0.000 claims description 7
- 230000002195 synergetic effect Effects 0.000 claims description 7
- 230000005855 radiation Effects 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 description 8
- 238000013461 design Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012634 optical imaging Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000007493 shaping process Methods 0.000 description 2
- 238000002922 simulated annealing Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000007655 standard test method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Landscapes
- Optical Communication System (AREA)
Abstract
The invention relates to the technical field of data processing, and discloses a spot parameter optimization method and a relevant device of an infrared LED. The spot parameter optimization method of the infrared LED comprises the following steps: initializing each initial spot parameter of the infrared LED to generate a first spot parameter set; and respectively carrying out spot adaptability evaluation on each first spot parameter to obtain a spot adaptability evaluation result set, and dynamically adjusting a preset spot parameter adjustment factor according to the spot adaptability evaluation result set to obtain a spot parameter self-adaptive adjustment factor. The invention can evaluate the performance of each spot parameter more accurately, thereby realizing more effective parameter optimization. Based on the optimization analysis of the performance index evaluation result, the method can accurately determine the final facula optimization parameter set, and effectively improve the overall performance of the infrared LED.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a spot parameter optimization method of an infrared LED and a related device.
Background
Infrared LEDs (light emitting diodes) are an important light source and are widely used in many fields, such as remote control technology, security monitoring, medical devices, etc. The efficacy of an infrared LED depends to a large extent on the characteristics of its spot, including the shape, distribution, and brightness of the spot. Therefore, optimizing the spot parameters of the infrared LED is critical to improving its overall performance.
Currently, the spot parameters of infrared LEDs are adjusted mainly by empirical design and standard test methods. These methods typically involve adjusting the physical structure of the LED, such as changing the lens design of the LED or adjusting the layout of internal electronics, and then evaluating the spot quality through a standardized test procedure. The method mainly depends on trial-and-error and iterative processes, is often low in efficiency, and is difficult to accurately control the light spot characteristics. The main technical defect of the prior art is that the adjustment and optimization process of the infrared LED spot parameters lacks flexibility and adaptability. Conventional methods often fail to effectively effect complex interactions between the spot parameters, resulting in time consuming and limited effectiveness of the optimization process. In addition, the existing method has limited capability in the aspect of processing multi-dimensional light spot characteristics, and is difficult to accurately evaluate and optimize the comprehensive characteristics of the light spot, such as shape, distribution, brightness and the like.
Therefore, a method capable of realizing efficient and accurate adjustment and optimization of infrared LED spot parameters is needed.
Disclosure of Invention
The invention provides a spot parameter optimization method and a spot parameter optimization device for an infrared LED, which are used for realizing efficient and accurate adjustment and optimization of spot parameters of the infrared LED.
The first aspect of the invention provides a spot parameter optimization method of an infrared LED, which comprises the following steps:
initializing each initial spot parameter of the infrared LED to generate a first spot parameter set; the first light spot parameter set comprises first light spot parameters corresponding to all initial light spot parameters;
respectively carrying out spot adaptability evaluation on each first spot parameter to obtain a spot adaptability evaluation result set, and dynamically adjusting a preset spot parameter adjustment factor according to the spot adaptability evaluation result set to obtain a spot parameter self-adaptive adjustment factor; the light spot fitness evaluation result set comprises light spot fitness evaluation results corresponding to all first light spot parameters;
based on the adaptive adjustment factor of the spot parameters, a nonlinear adjustment model of the infrared LED spot parameters is constructed, and based on the constructed nonlinear adjustment model of the infrared LED spot parameters, the first spot parameter set is adjusted to generate a second spot parameter set; the second light spot parameter set comprises second light spot parameters corresponding to the first light spot parameters;
testing the infrared LEDs by using the second light spot parameter sets to obtain light spot test data, and performing convolution processing on the light spot test data to generate multi-dimensional light spot characteristic vectors corresponding to each second light spot parameter; the multidimensional light spot characteristic vector corresponding to each second light spot parameter at least comprises the shape characteristic, the distribution characteristic and the brightness characteristic of the light spot;
Inputting the multi-dimensional facula characteristic vectors into a trained facula parameter performance evaluation model, and evaluating the performance index of each second facula parameter to obtain a performance index evaluation result of each second facula parameter; the light spot parameter performance evaluation model is obtained through training in advance;
and carrying out optimization analysis on the second light spot parameter sets based on the performance index evaluation result of each second light spot parameter to obtain final infrared LED light spot optimization parameter sets.
Optionally, in a first implementation manner of the first aspect of the present invention, initializing each initial spot parameter of the infrared LED to generate a first spot parameter set includes:
simulating the luminous characteristics of the infrared LED through a preset light source model to obtain multi-dimensional simulation data of the infrared LED; the multi-dimensional simulation data of the infrared LED comprises spectrum distribution simulation data of the infrared LED, radiation mode simulation data of the infrared LED and emission angle simulation data of the infrared LED;
defining a divergence angle of the infrared LED based on the multi-dimensional simulation data of the infrared LED, describing the divergence property of the infrared LED through a preset Gaussian beam model, and obtaining first data of the infrared LED;
Defining a propagation path of light rays in a preset optical system after the light rays are emitted from the infrared LED based on the multi-dimensional simulation data of the infrared LED, and obtaining second data of the infrared LED;
defining optical component parameters of the infrared LED based on the multidimensional simulation data of the infrared LED, controlling the light refraction angle, and optimizing the light spot form and parameters to obtain third data of the infrared LED;
and optimizing and adjusting the first data, the second data and the third data based on a preset optimization algorithm to generate a first light spot parameter set.
Optionally, in a second implementation manner of the first aspect of the present invention, the training process of the spot parameter performance evaluation model includes:
acquiring a multi-dimensional training data set; the multi-dimensional training data set comprises spot images of the infrared LEDs and performance evaluation indexes of the infrared LEDs under various conditions of ambient brightness, temperature and angle;
performing feature extraction on the multi-dimensional training data set to obtain first feature data and second feature data; the first characteristic data are based on the principal component data of the spot image of the infrared LED, and the second characteristic data are based on the principal component data of the performance evaluation index of the infrared LED;
Acquiring a multi-level self-adaptive deep learning network architecture; the multi-level self-adaptive deep learning network architecture comprises a primary feature perception layer, a medium-level feature combination layer and a high-level feature decision layer;
deep learning is carried out on the first characteristic data and the second characteristic data by utilizing a multi-level self-adaptive deep learning network architecture;
inputting the first characteristic data and the second characteristic data into the primary characteristic sensing layer for coding, and generating a target characteristic coding vector; the target feature coding vector is used for jointly representing morphological features of light spots and performance features of the infrared LEDs;
inputting the target feature coding vector to the intermediate feature joint layer for analysis, and generating a time sequence feature of the target feature coding vector dynamically changing along with an environment variable;
inputting the target feature coding vector and the time sequence feature into the advanced feature decision layer for evaluation to obtain a synergistic effect data set of the time sequence feature on the light spot performance of the infrared LED;
and carrying out repeated iterative optimization and fine adjustment on the multi-level self-adaptive deep learning network architecture based on a preset self-adaptive optimization algorithm until a synergic influence data set output by the multi-level self-adaptive deep learning network architecture reaches a preset performance target, so as to obtain a trained facula parameter performance evaluation model.
Optionally, in a third implementation manner of the first aspect of the present invention, after the step of obtaining the final infrared LED spot optimization parameter set, the method includes:
backing up the final infrared LED facula optimization parameter set to generate backup data;
the backup data is initially encrypted by using a preset security algorithm to form encrypted backup data with an initial protection level;
applying a preset primary encryption mechanism to execute a first round of encryption processing on the encrypted backup data of the initial protection level to obtain primary encrypted data;
adopting an encoding algorithm based on a preset primary encryption mechanism to encode primary encrypted data to generate primary encoded data;
based on the primary coded data, a secondary encryption mechanism different from the primary encryption mechanism is matched from a preset encryption mechanism database; the mapping relation of a secondary encryption mechanism which is matched with a primary encryption mechanism and is different from the primary encryption mechanism is stored in the database in advance according to the primary coding data;
performing a second round of encryption processing on the primary coded data according to the selected secondary encryption mechanism to generate secondary encrypted data;
and storing the secondary encrypted data into a database of the control center platform.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the security algorithm includes at least a hash function algorithm, a symmetric encryption algorithm, and a data signature algorithm.
The second aspect of the present invention provides a spot parameter optimizing apparatus for an infrared LED, the spot parameter optimizing apparatus for an infrared LED comprising:
the spot parameter optimizing device of the infrared LED comprises:
the initialization module is used for initializing each initial light spot parameter of the infrared LED to generate a first light spot parameter set; the first light spot parameter set comprises first light spot parameters corresponding to all initial light spot parameters;
the adjusting module is used for respectively carrying out light spot fitness evaluation on each first light spot parameter to obtain a light spot fitness evaluation result set, and dynamically adjusting a preset light spot parameter adjusting factor according to the light spot fitness evaluation result set to obtain a light spot parameter self-adaptive adjusting factor; the light spot fitness evaluation result set comprises light spot fitness evaluation results corresponding to all first light spot parameters;
the construction module is used for constructing a nonlinear adjustment model of the infrared LED light spot parameters based on the light spot parameter self-adaptive adjustment factors, and adjusting the first light spot parameter set based on the constructed nonlinear adjustment model of the infrared LED light spot parameters to generate a second light spot parameter set; the second light spot parameter set comprises second light spot parameters corresponding to the first light spot parameters;
The processing module is used for testing the infrared LEDs by using the second light spot parameter set to obtain light spot test data, and carrying out convolution processing on the light spot test data to generate a multi-dimensional light spot characteristic vector corresponding to each second light spot parameter; the multidimensional light spot characteristic vector corresponding to each second light spot parameter at least comprises the shape characteristic, the distribution characteristic and the brightness characteristic of the light spot;
the evaluation module is used for inputting the multi-dimensional facula characteristic vectors into the trained facula parameter performance evaluation model, and evaluating the performance index of each second facula parameter to obtain the performance index evaluation result of each second facula parameter; the light spot parameter performance evaluation model is obtained through training in advance;
and the analysis module is used for carrying out optimization analysis on the second light spot parameter sets based on the performance index evaluation result of each second light spot parameter to obtain final infrared LED light spot optimization parameter sets.
A third aspect of the present invention provides a spot parameter optimization apparatus for an infrared LED, including: a memory and at least one processor, the memory having instructions stored therein; and the at least one processor calls the instruction in the memory so that the spot parameter optimization device of the infrared LED executes the spot parameter optimization method of the infrared LED.
A fourth aspect of the invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the above-described method of spot parameter optimization of an infrared LED.
In the technical scheme provided by the invention, the beneficial effects are as follows: the invention provides a spot parameter optimization method and a related device of an infrared LED, wherein a first spot parameter set is generated by initializing each initial spot parameter of the infrared LED; respectively carrying out spot adaptability evaluation on each first spot parameter to obtain a spot adaptability evaluation result set, and dynamically adjusting a preset spot parameter adjustment factor according to the spot adaptability evaluation result set to obtain a spot parameter self-adaptive adjustment factor; based on the adaptive adjustment factor of the spot parameters, a nonlinear adjustment model of the infrared LED spot parameters is constructed, and based on the constructed nonlinear adjustment model of the infrared LED spot parameters, the first spot parameter set is adjusted to generate a second spot parameter set; testing the infrared LEDs by using the second light spot parameter sets to obtain light spot test data, and performing convolution processing on the light spot test data to generate multi-dimensional light spot characteristic vectors corresponding to each second light spot parameter; inputting the multi-dimensional facula characteristic vectors into a trained facula parameter performance evaluation model, and evaluating the performance index of each second facula parameter to obtain a performance index evaluation result of each second facula parameter; and carrying out optimization analysis on the second light spot parameter sets based on the performance index evaluation result of each second light spot parameter to obtain final infrared LED light spot optimization parameter sets. According to the invention, through the light spot fitness evaluation and the introduction of the self-adaptive adjustment factors, the adjustment of the light spot parameters can be dynamically optimized according to the actual performance feedback, so that the flexibility and the efficiency of the adjustment process are improved.
By adopting the nonlinear adjustment model, the method can better process complex interaction among the light spot parameters and realize finer and comprehensive light spot characteristic adjustment. By using convolution processing and multidimensional spot characteristic vectors, the shape, distribution and brightness characteristics of the spots can be comprehensively evaluated, and more comprehensive data support is provided for spot optimization. By inputting the multidimensional facula characteristic vector into the trained performance evaluation model, the performance of each facula parameter can be evaluated more accurately, thereby realizing more effective parameter optimization. Based on the optimization analysis of the performance index evaluation result, the method can accurately determine the final facula optimization parameter set, and effectively improve the overall performance of the infrared LED.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a spot parameter optimization method for an infrared LED according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an embodiment of a spot parameter optimization device for an infrared LED according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a spot parameter optimization method and a related device of an infrared LED. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a specific flow of an embodiment of the present invention is described below, referring to fig. 1, and an embodiment of a method for optimizing a spot parameter of an infrared LED in an embodiment of the present invention includes:
step 101, initializing each initial spot parameter of an infrared LED to generate a first spot parameter set; the first light spot parameter set comprises first light spot parameters corresponding to all initial light spot parameters;
it can be understood that the execution body of the invention can be a spot parameter optimizing device of an infrared LED, and can also be a terminal or a server, which is not limited in particular. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the implementation of step 101 is as follows:
initializing each initial spot parameter of the infrared LED to generate a first spot parameter set:
for the light beam emitted by the infrared LED, the initial light spot parameters comprise light intensity distribution, light spot size, divergence angle and the like. For each infrared LED, the initial light spot parameters are scanned and measured by using optical device simulation software or an optical testing device, and the spatial distribution characteristics and the beam parameters of the light spots are obtained.
For example, a beam shaping device (Beam Shaping Optics) is used to shape the beam emitted by the infrared LED, and parameters such as the intensity distribution, the spot size, and the spot shape of the beam are obtained by an optical imaging system. From these measurement data, the initial spot parameters for each infrared LED can be calculated.
The initial spot parameters are recorded to form a first spot parameter set, wherein the first spot parameter set comprises a first spot parameter corresponding to each infrared LED.
102, respectively carrying out spot adaptability evaluation on each first spot parameter to obtain a spot adaptability evaluation result set, and dynamically adjusting a preset spot parameter adjustment factor according to the spot adaptability evaluation result set to obtain a spot parameter self-adaptive adjustment factor; the light spot fitness evaluation result set comprises light spot fitness evaluation results corresponding to all first light spot parameters;
specifically, the implementation of step 102 is as follows:
respectively carrying out light spot adaptability evaluation on each first light spot parameter to obtain a light spot adaptability evaluation result set:
each first spot parameter is adaptively evaluated using an optical detection device or an imaging analysis system. The fitness evaluation may include indicators of spot uniformity, peak brightness, spatial distribution, and matching to the target scene. For example, the light spot is scanned using a detector array, the intensity distribution of the light spot is obtained, and an evaluation is made in combination with the characteristics of the target scene.
The evaluation results are arranged into a light spot fitness evaluation result set, wherein the light spot fitness evaluation result set comprises light spot fitness evaluation results corresponding to each first light spot parameter. The result set reflects the influence of different parameters on the quality of the light spot, and provides a basis for subsequent adjustment.
Dynamically adjusting a preset spot parameter adjustment factor according to a spot fitness evaluation result set to obtain a spot parameter self-adaptive adjustment factor:
and dynamically adjusting a preset spot parameter adjustment factor according to the spot fitness evaluation result set by using an optimization algorithm such as a genetic algorithm, a simulated annealing algorithm and the like. These adjustment factors can be used to adaptively adjust the lighting parameters of the infrared LED or the configuration of the optics to optimize the quality of the spot and to adapt to the target scene.
Step 103, constructing a nonlinear adjustment model of the infrared LED light spot parameters based on the light spot parameter self-adaptive adjustment factors, and adjusting the first light spot parameter set based on the constructed nonlinear adjustment model of the infrared LED light spot parameters to generate a second light spot parameter set; the second light spot parameter set comprises second light spot parameters corresponding to the first light spot parameters;
specifically, the implementation of step 103 is as follows:
based on the light spot parameter self-adaptive adjustment factor, constructing a nonlinear adjustment model of the light spot parameter of the infrared LED:
and constructing a nonlinear adjustment model of the infrared LED spot parameters according to the spot parameter self-adaptive adjustment factors by using a mathematical modeling method. This model may be based on a nonlinear functional relationship of factors, such as modeling and describing complex relationships between adjustment factors and spot parameters using polynomial fitting, neural network models, and the like.
For example, a machine learning method such as a Support Vector Machine (SVM) may be used to build a nonlinear adjustment model of the spot parameters according to a large amount of measured spot data and corresponding adjustment factors, so as to more accurately predict the relationship between the spot parameters and the adjustment factors.
Based on a constructed nonlinear adjustment model of infrared LED light spot parameters, adjusting the first light spot parameter set to generate a second light spot parameter set:
and adjusting each light spot parameter in the first light spot parameter set by using the constructed nonlinear adjustment model. And correcting each initial light spot parameter according to the preset light spot parameter self-adaptive adjustment factor and the constructed nonlinear adjustment model to obtain an adjusted second light spot parameter.
For example, parameters such as the size, the position and the shape of the light spot are adjusted in a nonlinear manner according to the model, so that the light spot is better adapted to different observation scenes and environmental conditions.
104, testing the infrared LEDs by using the second light spot parameter set to obtain light spot test data, and performing convolution processing on the light spot test data to generate a multi-dimensional light spot characteristic vector corresponding to each second light spot parameter; the multidimensional light spot characteristic vector corresponding to each second light spot parameter at least comprises the shape characteristic, the distribution characteristic and the brightness characteristic of the light spot;
Specifically, the implementation of step 104 is as follows:
testing the infrared LED by using the second light spot parameter set to obtain light spot test data:
the infrared LEDs are tested by using the testing equipment, and the testing is performed by using the high-precision position control system, the optical imaging equipment and the like based on parameter configuration in the second light spot parameter set. In the test process, recording data such as the intensity distribution, the shape characteristics, the edge definition and the like of the light spots to obtain a light spot test data set.
For example, a high-resolution infrared camera can be used for imaging light spots emitted by an infrared LED, and spatial distribution and intensity information of the light spots are obtained.
Convolving the light spot test data to generate multidimensional light spot characteristic vectors corresponding to each second light spot parameter:
and carrying out convolution processing on the light spot test data, and extracting multidimensional characteristics such as shape characteristics, distribution characteristics, brightness characteristics and the like of the light spots. The characteristic information of the light spot is converted into a multi-dimensional characteristic vector through image processing and signal processing technologies.
For example, the outline shape of the light spot can be extracted by using an edge detection algorithm, the spatial distribution characteristic of the light spot can be obtained by using an image processing technology, and the brightness characteristic of the light spot can be obtained by using luminosity calculation.
Step 105, inputting the multi-dimensional facula characteristic vectors into a trained facula parameter performance evaluation model, and evaluating the performance index of each second facula parameter to obtain a performance index evaluation result of each second facula parameter; the light spot parameter performance evaluation model is obtained through training in advance;
specifically, the implementation of step 105 is as follows:
inputting each multi-dimensional facula characteristic vector into a trained facula parameter performance evaluation model:
each multi-dimensional spot characteristic vector is input into the model using a spot parameter performance evaluation model that has been trained in advance. The model can be a performance evaluation model established based on machine learning technology such as Support Vector Machine (SVM), random Forest (Random Forest) and the like, and is used for evaluating various performance indexes of the facula parameters.
For example, a deep-learning Convolutional Neural Network (CNN) model may be utilized to train a performance assessment model of the spot characteristic vector to capture complex nonlinear relationships between the spot characteristics and performance metrics.
Evaluating the performance index of each second light spot parameter to obtain the performance index evaluation result of each second light spot parameter:
And evaluating the performance index of each second light spot parameter according to the output of the model. The performance index can comprise parameters such as resolution, contrast, smoothness and the like of the light spots, and comprehensive indexes such as adaptability, stability and the like.
For example, the light spot parameters are evaluated by using the model, so that performance evaluation results of the second light spot parameters are obtained, and the performance of the infrared LED light spot under different light spot parameter configurations is reflected.
And 106, performing optimization analysis on the second light spot parameter sets based on the performance index evaluation result of each second light spot parameter to obtain final infrared LED light spot optimization parameter sets.
Specifically, the implementation of step 106 is as follows:
and carrying out optimization analysis on the second light spot parameter sets based on the performance index evaluation result of each second light spot parameter:
and analyzing and optimizing the second light spot parameter set by utilizing an optimization algorithm (such as a genetic algorithm, a simulated annealing algorithm and the like) according to the performance index evaluation result of each second light spot parameter. And searching for the optimal second light spot parameter configuration by considering the trade-off and the mutual influence of various performance indexes.
For example, the performance index can be used as an objective function, and the performance index is comprehensively considered by utilizing a multi-objective optimization algorithm, so that performance optimization results under different parameter configurations are obtained.
Obtaining a final infrared LED facula optimization parameter set:
after the optimization analysis, a final infrared LED light spot optimization parameter set is obtained, and the parameter set can enable the infrared LED light spot to achieve optimal performance in aspects of shape characteristics, distribution characteristics, brightness characteristics and the like.
For example, a final infrared LED spot optimization parameter set is obtained according to the optimization analysis result, wherein the final infrared LED spot optimization parameter set comprises parameter configurations such as optimal spot shape, size, brightness adjustment and the like aiming at different application scenes.
Another embodiment of the spot parameter optimization method of the infrared LED in the embodiment of the present invention includes:
initializing each initial spot parameter of the infrared LED to generate a first spot parameter set, including:
simulating the luminous characteristics of the infrared LED through a preset light source model to obtain multi-dimensional simulation data of the infrared LED; the multi-dimensional simulation data of the infrared LED comprises spectrum distribution simulation data of the infrared LED, radiation mode simulation data of the infrared LED and emission angle simulation data of the infrared LED;
defining a divergence angle of the infrared LED based on the multi-dimensional simulation data of the infrared LED, describing the divergence property of the infrared LED through a preset Gaussian beam model, and obtaining first data of the infrared LED;
Defining a propagation path of light rays in a preset optical system after the light rays are emitted from the infrared LED based on the multi-dimensional simulation data of the infrared LED, and obtaining second data of the infrared LED;
defining optical component parameters of the infrared LED based on the multidimensional simulation data of the infrared LED, controlling the light refraction angle, and optimizing the light spot form and parameters to obtain third data of the infrared LED;
and optimizing and adjusting the first data, the second data and the third data based on a preset optimization algorithm to generate a first light spot parameter set.
In particular, the explanation of important terms:
multidimensional simulation data: the simulation data takes into account a plurality of dimensions or parameters, which herein refer to simulation results of spectral distribution, radiation pattern, emission angle, etc. over a plurality of properties.
Spectral distribution simulation data: data describing the spectral composition and distribution characteristics of light emitted by an infrared LED.
Radiation pattern simulation data: the spatially divergent nature of the light emitted by an infrared LED, such as the directionality, intensity distribution, etc. of the light is described.
Emission angle simulation data: the emission angle of light emitted by an infrared LED with respect to the LED surface is described.
Divergence angle: the angular range over which the light beam from the light source diverges from the original ray is described.
Gaussian beam model: a mathematical model describing the intensity distribution of a light beam is typically used to describe the change in intensity of a light wave as it propagates spatially.
First data, second data, third data: and generating according to the multidimensional simulation data of the infrared LED and using the multidimensional simulation data to optimize a group of parameter data obtained in the light spot parameter process.
Light propagation path: describing the route that light travels from a source to a destination.
Optical component parameters: parameters of each component constituting the optical system, such as the shape of the lens, the radius of curvature, the refractive index of the material, and the like, are described.
The following are the detailed implementation steps of the scheme:
light emitting characteristics of the multi-dimensional analog infrared LED:
and simulating the luminous characteristics of the infrared LEDs by using a preset light source model to generate multi-dimensional simulation data. This includes analog data of the spectral distribution, radiation pattern, and emission angle of the infrared LED.
Defining the divergence angle of the infrared LED:
based on the simulation data, the divergence angle of the infrared LED is determined. Using a gaussian beam model, describing the divergent properties of the LED, first data about the beam intensity distribution is obtained.
Simulation of the light propagation path:
according to the multidimensional simulation data of the infrared LED, defining a propagation path of light rays in a preset optical system. This step generates second data regarding the light propagation efficiency and path characteristics.
Defining optical component parameters:
using the simulation data, optical component parameters of the infrared LED, such as the shape and refractive index of the lens, are defined. And optimizing the form and parameters of the light spot by controlling the refraction angle, and generating third data.
Optimizing the light spot parameters:
and analyzing and optimizing the first data, the second data and the third data by applying a preset optimization algorithm to achieve the optimal spot characteristics such as the size, the shape, the uniformity and the like of the spot. The final spot parameter set is generated in this process.
In the embodiment of the invention, the beneficial effects are as follows: the embodiment of the invention can accurately control the light spot characteristics of the infrared LED, which is important to improving the application effect of the optical system in the fields such as safety monitoring, sensor technology, medical imaging and the like. By optimizing the spot parameters, the accuracy and efficiency of the optical system can be improved, thereby achieving higher performance and reliability in various applications.
Another embodiment of the spot parameter optimization method of the infrared LED in the embodiment of the present invention includes: the training process of the facula parameter performance evaluation model comprises the following steps:
acquiring a multi-dimensional training data set; the multi-dimensional training data set comprises spot images of the infrared LEDs and performance evaluation indexes of the infrared LEDs under various conditions of ambient brightness, temperature and angle;
Performing feature extraction on the multi-dimensional training data set to obtain first feature data and second feature data; the first characteristic data are based on the principal component data of the spot image of the infrared LED, and the second characteristic data are based on the principal component data of the performance evaluation index of the infrared LED;
acquiring a multi-level self-adaptive deep learning network architecture; the multi-level self-adaptive deep learning network architecture comprises a primary feature perception layer, a medium-level feature combination layer and a high-level feature decision layer;
deep learning is carried out on the first characteristic data and the second characteristic data by utilizing a multi-level self-adaptive deep learning network architecture;
inputting the first characteristic data and the second characteristic data into the primary characteristic sensing layer for coding, and generating a target characteristic coding vector; the target feature coding vector is used for jointly representing morphological features of light spots and performance features of the infrared LEDs;
inputting the target feature coding vector to the intermediate feature joint layer for analysis, and generating a time sequence feature of the target feature coding vector dynamically changing along with an environment variable;
inputting the target feature coding vector and the time sequence feature into the advanced feature decision layer for evaluation to obtain a synergistic effect data set of the time sequence feature on the light spot performance of the infrared LED;
And carrying out repeated iterative optimization and fine adjustment on the multi-level self-adaptive deep learning network architecture based on a preset self-adaptive optimization algorithm until a synergic influence data set output by the multi-level self-adaptive deep learning network architecture reaches a preset performance target, so as to obtain a trained facula parameter performance evaluation model.
In particular, the explanation of important terms:
light spot parameter performance evaluation model: a deep learning model is used to evaluate the impact of spot parameters (e.g., size, shape, uniformity, etc.) generated by an infrared LED on overall performance.
Multidimensional training data set: including data collected from multiple dimensions, such as infrared LED spot images and associated performance metrics under different ambient brightness, temperature, and angle conditions.
First feature data and second feature data: characteristic data obtained based on the main component of the infrared LED flare image and the main component of the infrared LED performance evaluation index are respectively represented.
Multi-level self-adaptive deep learning network architecture: the deep learning model consists of multiple layers of network layers, wherein each layer corresponds to different layers of characteristic processing and decision making processes respectively and can be adjusted in a self-adaptive mode according to input data.
Primary feature perception layer: the hierarchy in the deep learning model is mainly used for sensing basic characteristics of input data.
Intermediate level feature federation layer: and the hierarchy in the deep learning model is used for further combining and analyzing the features extracted by the primary layer.
Advanced feature decision layer: and the hierarchy in the deep learning model is used for making final judgment or decision according to the resolved characteristics.
Target feature encoding vector: a multidimensional vector containing the morphological characteristics and the performance characteristics of the light spots is obtained by encoding a primary characteristic perception layer.
Time series characteristics: a series of time ordered data points reflect the pattern of the change in the target feature over time.
Synergistic effect dataset: the method comprises the step of integrating the time series characteristic and the environment variable together on the comprehensive data set of the influence generated by the light spot performance of the infrared LED.
Adaptive optimization algorithm: an optimization algorithm capable of self-adjusting parameters based on performance feedback is used to improve the performance of a model.
Iterative optimization and fine tuning: and (3) repeating the optimization process, and fine-tuning the model parameters for each iteration to improve the performance until the preset target is reached.
The trained facula parameter performance evaluation model: after repeated iterative optimization and fine adjustment, a trained model which can accurately evaluate the influence of the infrared LED light spot attribute on the performance is obtained.
The following are the detailed implementation steps of the scheme:
collecting a multi-dimensional training dataset:
and collecting spot images of the infrared LEDs and corresponding performance evaluation indexes under various environmental conditions (different brightness, temperature and angles) to form a multi-dimensional training data set.
And (3) extracting characteristics:
and carrying out feature extraction on the multi-dimensional training data set, and respectively extracting first feature data based on the facula image and second feature data based on the performance evaluation index. Principal Component Analysis (PCA) techniques are applied for dimension reduction to obtain key features.
Constructing a multi-level self-adaptive deep learning network architecture:
a deep learning model is designed that includes a primary feature perception layer (for identifying low-level features), a mid-level feature federation layer (for integrating primary-level features), and a high-level feature decision layer (for making performance evaluation decisions).
Deep learning is carried out:
and enabling the model to learn the first characteristic data and the second characteristic data, and capturing the complex relation between the facula image and the performance index.
Encoding characteristic data:
and inputting the feature data into a primary feature perception layer to generate a target feature coding vector containing the light spot morphology and performance features.
Analyzing time sequence characteristics:
and sending the target feature coding vector into a middle-level feature combination layer, analyzing the dynamic change of the target feature coding vector along with the environment variable, and generating time sequence features.
Evaluating the light spot performance:
and (3) combining the time sequence features and the target feature coding vector, and evaluating the light spot performance through an advanced feature decision layer. A data set is generated reflecting the effect of the spot performance as a function of the environment.
Iterative optimization and fine tuning:
and performing repeated iterative optimization and fine tuning on the deep learning model by using an adaptive optimization algorithm. And adjusting network parameters to improve the accuracy of performance evaluation until a preset performance target is met.
Obtaining a trained model:
after optimization and adjustment, the model can accurately evaluate the influence of the light spot parameters on the performance of the infrared LED under different environmental conditions. The trained model can be used for guiding the design and manufacture of infrared LED light spots, and ensures that the infrared LED light spots have optimal performance under actual use conditions.
In the embodiment of the invention, the beneficial effects are as follows: the embodiment of the invention can improve the performance of the infrared LED in various application scenes, reduce the trial-and-error cost in the development process and accelerate the production period. The deep learning model is utilized to comprehensively evaluate the LED facula performance, a plurality of influencing factors are considered, and the accuracy and reliability of evaluation are improved. Through the training data set covering various environmental conditions, the model can predict and optimize the performance of the infrared LED under different use scenes, and the environmental adaptability of the product is enhanced. The trained model can be directly used for guiding the design parameter adjustment of the light spots so as to obtain better performance indexes and optimize the design flow. The deep learning network architecture provided by the scheme has good flexibility, can adapt to new data and conditions, and is easy to expand to adapt to more complex application scenes in the future.
Another embodiment of the spot parameter optimization method of the infrared LED in the embodiment of the present invention includes: after the step of obtaining the final infrared LED light spot optimization parameter set, the method comprises the following steps:
backing up the final infrared LED facula optimization parameter set to generate backup data;
the backup data is initially encrypted by using a preset security algorithm to form encrypted backup data with an initial protection level;
applying a preset primary encryption mechanism to execute a first round of encryption processing on the encrypted backup data of the initial protection level to obtain primary encrypted data;
adopting an encoding algorithm based on a preset primary encryption mechanism to encode primary encrypted data to generate primary encoded data;
based on the primary coded data, a secondary encryption mechanism different from the primary encryption mechanism is matched from a preset encryption mechanism database; the mapping relation of a secondary encryption mechanism which is matched with a primary encryption mechanism and is different from the primary encryption mechanism is stored in the database in advance according to the primary coding data;
performing a second round of encryption processing on the primary coded data according to the selected secondary encryption mechanism to generate secondary encrypted data;
And storing the secondary encrypted data into a database of the control center platform.
In particular, important terms explain:
infrared LED spot optimization parameter set: this is a set of adjusted parameters that are used to optimize the spot emitted by the infrared LED for optimal performance.
Backup data: to avoid data loss, copies of important information are stored in a secure location.
Initial encryption: the first encryption operation performed on the data is intended to provide a basic level of protection.
Encrypted backup data of an initial protection level: the data obtained by the initial encryption, which is an encrypted state of the data backup, protects the data from unauthorized access.
Primary encryption mechanism: this is the algorithm or method used by the preset initial encryption step to perform a first round of encryption processing on the data.
First round encryption processing: and performing first-round encryption operation on the data by using a preset primary encryption mechanism.
Primary encoded data: based on the first-order encryption, the data processed by the coding algorithm is further used.
Secondary encryption mechanism: this is an encryption algorithm or method that differs from the primary encryption scheme to perform an additional layer of security on an encrypted data set, thereby achieving a higher level of protection.
Second round encryption processing: and further encrypting the primary coded data by adopting a secondary encryption mechanism on the basis of the first round of encryption processing.
Encryption mechanism database: a database storing various encryption mechanisms and a mapping relation of a secondary encryption mechanism corresponding to the primary coded data.
Two-stage encrypted data: the resulting data is processed by a secondary encryption mechanism that provides further encryption protection against primary encrypted data.
And a control center platform: a centralized platform for managing and storing important data, including data that has been subjected to multiple encryption.
Distinction and association:
the first-level encryption mechanism and the second-level encryption mechanism are connected in that the first-level encryption mechanism and the second-level encryption mechanism are algorithms or methods for protecting data security, and form a layered encryption strategy together to enhance data protection. The difference is that the secondary encryption mechanism is an additional security measure based on the primary encryption, and different encryption algorithms are generally selected to ensure that data is still protected even if the primary encryption is broken.
The relationship of the first round of encryption processing and the second round of encryption processing is order dependent. The first round of encryption is based on encryption steps, and the second round of encryption is an additional security layer based on the first round of encryption. The purpose of the second round of encryption processing is to enable the secondary encryption to protect the security of the data even if an attacker somehow breaks through the primary encryption.
Based on the information provided, the following is one specific embodiment of data protection and encryption for an infrared LED spot optimization parameter set:
1. acquisition and backup of infrared LED light spot optimization parameter set
Step 1: firstly, an optimal spot parameter set of the infrared LED is obtained through a series of testing and measuring processes. These parameters may include the power, emission angle, wavelength, etc. of the LED.
Step 2: and backing up the obtained final infrared LED light spot optimization parameter set to generate backup data. This step ensures that when the original data is lost or corrupted, it can be restored to the current optimal state.
2. Data encryption and protection
Step 3: and carrying out initial encryption on the backup data by using a preset security algorithm to form encrypted backup data with an initial protection level. This step is to ensure the basic security of the backup data.
Step 4: and executing a first round of encryption processing on the encrypted backup data of the initial protection level by applying a preset primary encryption mechanism, thereby obtaining primary encrypted data. This primary encryption mechanism may be a common encryption standard such as AES or RSA.
Step 5: and adopting an encoding algorithm based on a preset primary encryption mechanism to encode the primary encrypted data, and generating primary encoded data. This step further complicates the data making it more difficult to crack.
3. Advanced encryption process
Step 6: and based on the primary coded data, matching a secondary encryption mechanism different from the primary encryption mechanism from a preset encryption mechanism database. The database stores different encryption mechanisms and mapping relations thereof in advance to ensure that a most appropriate secondary encryption mechanism is selected for each primary encryption data.
Step 7: and performing a second round of encryption processing on the primary coded data according to the selected secondary encryption mechanism, thereby generating secondary encrypted data. The purpose of this step is to provide an additional layer of security so that the data is still protected even if the primary encryption is broken.
4. Data storage and management
Step 8: and finally, storing the processed secondary encryption data into a database of the control center platform. This control center platform not only provides a secure data storage environment, but may also contain tools and protocols for monitoring and managing data security.
In the embodiment of the invention, the beneficial effects are as follows: the embodiment of the invention greatly enhances the security of data through a two-stage encryption mechanism. Even if the primary encryption is broken, the secondary encryption still protects the data from illegal access. The multi-level encryption and encoding process allows data to remain highly confidential even when transmitted or stored in an unsafe environment. By backing up the important infrared LED light spot optimization parameter set and encrypting the backup data, the original data can be effectively recovered even if lost or damaged. By using a preset encryption mechanism database, the scheme can flexibly select a proper encryption mechanism according to different data characteristics and security requirements, and the adaptability and the efficiency of the scheme are improved. The encrypted data is stored in the database of the control center platform, so that the centralized management and the monitoring of the safety state of the data are facilitated, and meanwhile, the updating and the maintenance of the data are facilitated.
Another embodiment of the spot parameter optimization method of the infrared LED in the embodiment of the present invention includes: the security algorithm at least comprises a hash function algorithm, a symmetric encryption algorithm and a data signature algorithm.
The method for optimizing the spot parameters of the infrared LED in the embodiment of the present invention is described above, and the device for optimizing the spot parameters of the infrared LED in the embodiment of the present invention is described below, referring to fig. 2, and one embodiment of the device for optimizing the spot parameters of the infrared LED in the embodiment of the present invention includes:
the spot parameter optimizing device of the infrared LED comprises:
the initialization module is used for initializing each initial light spot parameter of the infrared LED to generate a first light spot parameter set; the first light spot parameter set comprises first light spot parameters corresponding to all initial light spot parameters;
the adjusting module is used for respectively carrying out light spot fitness evaluation on each first light spot parameter to obtain a light spot fitness evaluation result set, and dynamically adjusting a preset light spot parameter adjusting factor according to the light spot fitness evaluation result set to obtain a light spot parameter self-adaptive adjusting factor; the light spot fitness evaluation result set comprises light spot fitness evaluation results corresponding to all first light spot parameters;
The construction module is used for constructing a nonlinear adjustment model of the infrared LED light spot parameters based on the light spot parameter self-adaptive adjustment factors, and adjusting the first light spot parameter set based on the constructed nonlinear adjustment model of the infrared LED light spot parameters to generate a second light spot parameter set; the second light spot parameter set comprises second light spot parameters corresponding to the first light spot parameters;
the processing module is used for testing the infrared LEDs by using the second light spot parameter set to obtain light spot test data, and carrying out convolution processing on the light spot test data to generate a multi-dimensional light spot characteristic vector corresponding to each second light spot parameter; the multidimensional light spot characteristic vector corresponding to each second light spot parameter at least comprises the shape characteristic, the distribution characteristic and the brightness characteristic of the light spot;
the evaluation module is used for inputting the multi-dimensional facula characteristic vectors into the trained facula parameter performance evaluation model, and evaluating the performance index of each second facula parameter to obtain the performance index evaluation result of each second facula parameter; the light spot parameter performance evaluation model is obtained through training in advance;
and the analysis module is used for carrying out optimization analysis on the second light spot parameter sets based on the performance index evaluation result of each second light spot parameter to obtain final infrared LED light spot optimization parameter sets.
The invention also provides a spot parameter optimizing device of the infrared LED, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor executes the steps of the spot parameter optimizing method of the infrared LED in the embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, where the instructions when executed on a computer cause the computer to perform the steps of the method for optimizing a spot parameter of an infrared LED.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The spot parameter optimization method of the infrared LED is characterized by comprising the following steps of:
initializing each initial spot parameter of the infrared LED to generate a first spot parameter set; the first light spot parameter set comprises first light spot parameters corresponding to all initial light spot parameters;
respectively carrying out spot adaptability evaluation on each first spot parameter to obtain a spot adaptability evaluation result set, and dynamically adjusting a preset spot parameter adjustment factor according to the spot adaptability evaluation result set to obtain a spot parameter self-adaptive adjustment factor; the light spot fitness evaluation result set comprises light spot fitness evaluation results corresponding to all first light spot parameters;
Based on the adaptive adjustment factor of the spot parameters, a nonlinear adjustment model of the infrared LED spot parameters is constructed, and based on the constructed nonlinear adjustment model of the infrared LED spot parameters, the first spot parameter set is adjusted to generate a second spot parameter set; the second light spot parameter set comprises second light spot parameters corresponding to the first light spot parameters;
testing the infrared LEDs by using the second light spot parameter sets to obtain light spot test data, and performing convolution processing on the light spot test data to generate multi-dimensional light spot characteristic vectors corresponding to each second light spot parameter; the multidimensional light spot characteristic vector corresponding to each second light spot parameter at least comprises the shape characteristic, the distribution characteristic and the brightness characteristic of the light spot;
inputting the multi-dimensional facula characteristic vectors into a trained facula parameter performance evaluation model, and evaluating the performance index of each second facula parameter to obtain a performance index evaluation result of each second facula parameter; the light spot parameter performance evaluation model is obtained through training in advance;
and carrying out optimization analysis on the second light spot parameter sets based on the performance index evaluation result of each second light spot parameter to obtain final infrared LED light spot optimization parameter sets.
2. The method for optimizing spot parameters of an infrared LED according to claim 1, wherein initializing each initial spot parameter of the infrared LED to generate a first spot parameter set comprises:
simulating the luminous characteristics of the infrared LED through a preset light source model to obtain multi-dimensional simulation data of the infrared LED; the multi-dimensional simulation data of the infrared LED comprises spectrum distribution simulation data of the infrared LED, radiation mode simulation data of the infrared LED and emission angle simulation data of the infrared LED;
defining a divergence angle of the infrared LED based on the multi-dimensional simulation data of the infrared LED, describing the divergence property of the infrared LED through a preset Gaussian beam model, and obtaining first data of the infrared LED;
defining a propagation path of light rays in a preset optical system after the light rays are emitted from the infrared LED based on the multi-dimensional simulation data of the infrared LED, and obtaining second data of the infrared LED;
defining optical component parameters of the infrared LED based on the multidimensional simulation data of the infrared LED, controlling the light refraction angle, and optimizing the light spot form and parameters to obtain third data of the infrared LED;
and optimizing and adjusting the first data, the second data and the third data based on a preset optimization algorithm to generate a first light spot parameter set.
3. The method for optimizing spot parameters of an infrared LED according to claim 1, wherein the training process of the spot parameter performance evaluation model comprises:
acquiring a multi-dimensional training data set; the multi-dimensional training data set comprises spot images of the infrared LEDs and performance evaluation indexes of the infrared LEDs under various conditions of ambient brightness, temperature and angle;
performing feature extraction on the multi-dimensional training data set to obtain first feature data and second feature data; the first characteristic data are based on the principal component data of the spot image of the infrared LED, and the second characteristic data are based on the principal component data of the performance evaluation index of the infrared LED;
acquiring a multi-level self-adaptive deep learning network architecture; the multi-level self-adaptive deep learning network architecture comprises a primary feature perception layer, a medium-level feature combination layer and a high-level feature decision layer;
deep learning is carried out on the first characteristic data and the second characteristic data by utilizing a multi-level self-adaptive deep learning network architecture;
inputting the first characteristic data and the second characteristic data into the primary characteristic sensing layer for coding, and generating a target characteristic coding vector; the target feature coding vector is used for jointly representing morphological features of light spots and performance features of the infrared LEDs;
Inputting the target feature coding vector to the intermediate feature joint layer for analysis, and generating a time sequence feature of the target feature coding vector dynamically changing along with an environment variable;
inputting the target feature coding vector and the time sequence feature into the advanced feature decision layer for evaluation to obtain a synergistic effect data set of the time sequence feature on the light spot performance of the infrared LED;
and carrying out repeated iterative optimization and fine adjustment on the multi-level self-adaptive deep learning network architecture based on a preset self-adaptive optimization algorithm until a synergic influence data set output by the multi-level self-adaptive deep learning network architecture reaches a preset performance target, so as to obtain a trained facula parameter performance evaluation model.
4. The method for optimizing spot parameters of an infrared LED according to claim 1, wherein after the step of obtaining a final set of spot optimization parameters of the infrared LED, the method comprises:
backing up the final infrared LED facula optimization parameter set to generate backup data;
the backup data is initially encrypted by using a preset security algorithm to form encrypted backup data with an initial protection level;
applying a preset primary encryption mechanism to execute a first round of encryption processing on the encrypted backup data of the initial protection level to obtain primary encrypted data;
Adopting an encoding algorithm based on a preset primary encryption mechanism to encode primary encrypted data to generate primary encoded data;
based on the primary coded data, a secondary encryption mechanism different from the primary encryption mechanism is matched from a preset encryption mechanism database; the mapping relation of a secondary encryption mechanism which is matched with a primary encryption mechanism and is different from the primary encryption mechanism is stored in the database in advance according to the primary coding data;
performing a second round of encryption processing on the primary coded data according to the selected secondary encryption mechanism to generate secondary encrypted data;
and storing the secondary encrypted data into a database of the control center platform.
5. The method for optimizing spot parameters of an infrared LED as recited in claim 4, wherein,
the security algorithm at least comprises a hash function algorithm, a symmetric encryption algorithm and a data signature algorithm.
6. The spot parameter optimizing device of the infrared LED is characterized by comprising:
the initialization module is used for initializing each initial light spot parameter of the infrared LED to generate a first light spot parameter set; the first light spot parameter set comprises first light spot parameters corresponding to all initial light spot parameters;
The adjusting module is used for respectively carrying out light spot fitness evaluation on each first light spot parameter to obtain a light spot fitness evaluation result set, and dynamically adjusting a preset light spot parameter adjusting factor according to the light spot fitness evaluation result set to obtain a light spot parameter self-adaptive adjusting factor; the light spot fitness evaluation result set comprises light spot fitness evaluation results corresponding to all first light spot parameters;
the construction module is used for constructing a nonlinear adjustment model of the infrared LED light spot parameters based on the light spot parameter self-adaptive adjustment factors, and adjusting the first light spot parameter set based on the constructed nonlinear adjustment model of the infrared LED light spot parameters to generate a second light spot parameter set; the second light spot parameter set comprises second light spot parameters corresponding to the first light spot parameters;
the processing module is used for testing the infrared LEDs by using the second light spot parameter set to obtain light spot test data, and carrying out convolution processing on the light spot test data to generate a multi-dimensional light spot characteristic vector corresponding to each second light spot parameter; the multidimensional light spot characteristic vector corresponding to each second light spot parameter at least comprises the shape characteristic, the distribution characteristic and the brightness characteristic of the light spot;
The evaluation module is used for inputting the multi-dimensional facula characteristic vectors into the trained facula parameter performance evaluation model, and evaluating the performance index of each second facula parameter to obtain the performance index evaluation result of each second facula parameter; the light spot parameter performance evaluation model is obtained through training in advance;
and the analysis module is used for carrying out optimization analysis on the second light spot parameter sets based on the performance index evaluation result of each second light spot parameter to obtain final infrared LED light spot optimization parameter sets.
7. An infrared LED spot parameter optimization apparatus, characterized in that the infrared LED spot parameter optimization apparatus comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the spot parameter optimization device of the infrared LED to perform the spot parameter optimization method of the infrared LED according to any one of claims 1-5.
8. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement a spot parameter optimization method of an infrared LED according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410104621.8A CN117634322B (en) | 2024-01-25 | 2024-01-25 | Infrared LED facula parameter optimization method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410104621.8A CN117634322B (en) | 2024-01-25 | 2024-01-25 | Infrared LED facula parameter optimization method and related device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117634322A CN117634322A (en) | 2024-03-01 |
| CN117634322B true CN117634322B (en) | 2024-04-02 |
Family
ID=90032502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410104621.8A Active CN117634322B (en) | 2024-01-25 | 2024-01-25 | Infrared LED facula parameter optimization method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117634322B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101202015A (en) * | 2007-08-22 | 2008-06-18 | 深圳市同洲电子股份有限公司 | Lightness data obtaining method and device for gamma correction of LED |
| JP2015132866A (en) * | 2014-01-09 | 2015-07-23 | 日立マクセル株式会社 | Ray model forming method and lighting device design support apparatus using same |
| CN113935948A (en) * | 2021-09-10 | 2022-01-14 | 南京邮电大学 | Grating image target positioning optimization and wavelength characteristic analysis method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI439676B (en) * | 2012-03-29 | 2014-06-01 | Nat Applied Res Laboratories | An LED white light quality detection method and device |
-
2024
- 2024-01-25 CN CN202410104621.8A patent/CN117634322B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101202015A (en) * | 2007-08-22 | 2008-06-18 | 深圳市同洲电子股份有限公司 | Lightness data obtaining method and device for gamma correction of LED |
| JP2015132866A (en) * | 2014-01-09 | 2015-07-23 | 日立マクセル株式会社 | Ray model forming method and lighting device design support apparatus using same |
| CN113935948A (en) * | 2021-09-10 | 2022-01-14 | 南京邮电大学 | Grating image target positioning optimization and wavelength characteristic analysis method and device |
Non-Patent Citations (2)
| Title |
|---|
| LED近场光学模型与直下式背光源透镜的设计优化;钱可元;;光学学报;20150510(05);第0522001-1-0522001-6页 * |
| Thermal simulation and optimization design on a high-power LED spot lamp;Yu Gui-ying 等;Optoelectronics Letters;20111231;第117-121页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117634322A (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Martinez-Moyano et al. | A behavioral theory of insider-threat risks: A system dynamics approach | |
| US8270719B2 (en) | Gem pattern matching algorithm to determine the percentage match of a target gem pattern to a database of gem patterns | |
| CN111787011B (en) | Intelligent analysis and early warning system, method and storage medium for security threat of information system | |
| EP3734508A1 (en) | Classification model for controlling a manufacturing process | |
| US20220245048A1 (en) | System and methods for generating fault indications for an additive manufacturing process based on a probabilistic comparison of the outputs of multiple process models to measured sensor data | |
| CN117634322B (en) | Infrared LED facula parameter optimization method and related device | |
| Martineau et al. | Neural network architectures and feature extraction for lumber production prediction | |
| Hintersdorf et al. | To trust or not to trust prediction scores for membership inference attacks | |
| KR100524649B1 (en) | Risk analysis system for information assets | |
| Ezeme et al. | An imputation-based augmented anomaly detection from large traces of operating system events | |
| JP4711131B2 (en) | Pixel group parameter calculation method and pixel group parameter calculation apparatus | |
| Atoum et al. | A classification scheme for cybersecurity models | |
| KR20230121571A (en) | Device and method for determining adversarial patches for a machine learning system | |
| García-Gutiérrez et al. | A comparative study between two regression methods on LiDAR data: A case study | |
| CN112989339B (en) | Machine learning-based malicious code intrusion detection method for GCC compiler | |
| Zhai et al. | Information integration of force sensing and machine vision for in‐shell shrivelled walnut detection based on the golden‐section search optimal discrimination threshold | |
| US20200389482A1 (en) | Software application for continually assessing, processing, and remediating cyber-risk in real time | |
| Brooks et al. | Atmospheric simulation using a liquid crystal wavefront-controlling device | |
| CN117993723B (en) | Business process information system based on data integration and operation method | |
| US20220076148A1 (en) | Information processing device and information processing method | |
| Wong et al. | Learning System Security Compliance for Banking | |
| CN117541483B (en) | Structural performance evaluation method and system for diffusion plate | |
| CN118051949B (en) | AI-based platform content security inspection method, AI-based platform content security inspection device and storage medium | |
| Jahaj et al. | Testing Photometric Stereo Applications | |
| Jain et al. | Fake image detection using machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |